rl_and_robotics.md

Reinforencement Learning and Robotics

Reinforencement Learning

• Key Papers in Deep RL.
• [2013 NIPS] Playing Atari with Deep Reinforcement Learning, [paper], [bibtex], [blog], sources: [kuz/DeepMind-Atari-Deep-Q-Learner], [ethanscho/dqn-atari-tensorflow], [carpedm20/deep-rl-tensorflow].
• [2014 ICML] Deterministic Policy Gradient Algorithms, [paper], [supplementary], [bibtex], [blog], sources: [cookbenjamin/DDPG].
• [2015 Nature] DQN: Human-level control through deep reinforcement learning, [paper], [bibtex], [blog], [code-page], sources: [openai/baselines], [hill-a/stable-baselines].
• [2016 ICML] Asynchronous Methods for Deep Reinforcement Learning, [paper], [bibtex], [supplementary], sources: [miyosuda/async_deep_reinforce].
• [2016 ICML] Dueling DQN: Dueling Network Architectures for Deep Reinforcement Learning, [paper], [bibtex].
• [2016 ICLR] Prioritized DQN: Prioritized Experience Replay, [paper], [bibtex], [blog], sources: [Damcy/prioritized-experience-replay].
• [2017 ICLR] An Actor Critic Algorithm for Structured Prediction, [paper], [bibtex], sources: [rizar/actor-critic-public].
• [2017 ICML] Categorical DQN: A Distributional Perspective on Reinforcement Learning, [paper], [bibtex], sources: [Silvicek/distributional-dqn].
• [2017 ICML] Curiosity-driven Exploration by Self-supervised Prediction, [paper], [bibtex], sources: [pathak22/noreward-rl].
• [2018 ICLR] NoisyNet DQN: Noisy Networks for Exploration, [paper], [bibtex], sources: [Kaixhin/NoisyNet-A3C].
• [2018 AAAI] Rainbow: Combining Improvements in Deep Reinforcement Learning, [paper], [bibtex], sources: [Kaixhin/Rainbow].
• [2018 AAAI] Deep Reinforcement Learning that Matters, [paper], [bibtex], sources: [Breakend/DeepReinforcementLearningThatMatters].
• [2019 TICS] Reinforcement Learning, Fast and Slow, [paper], [bibtex].
• [2020 ICML] Intrinsic Reward Driven Imitation Learning via Generative Model, [paper], [bibtex].

Robotics and RL Applications

• [2014 ACL] Learning Spatial Knowledge for Text to 3D Scene Generation, [paper], [bibtex].
• [2015 IROS] Neural Network based Model for Visual-motor Integration Learning of Robot’s Drawing Behavior: Association of a Drawing Motion from a Drawn Image, [paper], [bibtex].
• [2016 ICRA] Learning to Generalize 3D Spatial Relationships, [paper], [bibtex].
• [2016 TCDS] Spatial Concept Acquisition for a Mobile Robot That Integrates Self-Localization and Unsupervised Word Discovery From Spoken Sentences, [paper], [bibtex].
• [2017 AAAI] Natural Language Acquisition and Grounding for Embodied Robotic Systems, [paper], [bibtex].
• [2017 PMLR] Opportunistic Active Learning for Grounding Natural Language Descriptions, [paper], [bibtex], sources: [thomason-jesse/perception_classifiers].
• [2018 ArXiv] A Learning Framework for High Precision Industrial Assembly, [paper], [bibtex].
• [2018 AAAI] Guiding Exploratory Behaviors for Multi-Modal Grounding of Linguistic Descriptions, [paper], [bibtex], sources: [thomason-jesse/object_exploration].
• [2018 Robotics] Learning Task-Oriented Grasping for Tool Manipulation from Simulated Self-Supervision, [paper], [bibtex].
• [2018 ICRA] Text2Action: Generative Adversarial Synthesis from Language to Action, [paper], [bibtex].
• [2018 CoRL] QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation, [paper], [bibtex], [homepage], sources: [DeepX-inc/machina].
• [2018 CoRL] Sim-to-Real Transfer with Neural-Augmented Robot Simulation, [paper], [bibtex], sources: [aalitaiga/sim-to-real].
• [2018 CoRL] Task-Embedded Control Networks for Few-Shot Imitation Learning, [paper], [bibtex], sources: [stepjam/TecNets].
• [2018 ICML] QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning, [paper], [bibtex], [supplementary].
• [2018 ICRA] Vision-Based Multi-Task Manipulation for Inexpensive Robots Using End-To-End Learning from Demonstration, [paper], [bibtex].
• [2018 AAAI] Learning Interpretable Spatial Operations in a Rich 3D Blocks World, [paper], [bibtex], [dataset], sources: [ybisk/GroundedLanguage].
• [2018 NeurIPS] Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding, [paper], [bibtex], sources: [kexinyi/ns-vqa].
• [2018 RSS] Push-Net: Deep Planar Pushing for Objects with Unknown Physical Properties, [paper], [bibtex], sources: [ljklonepiece/PushNet].
• [2019 IROS] Robot Artist Performs Cartoon Style Facial Portrait Painting, [paper], [bibtex].
• [2019 CVPR] Sim-to-Real via Sim-to-Sim: Data-efficient Robotic Grasping via Randomized-to-Canonical Adaptation Networks, [paper], [bibtex], [homepage].
• [2019 TII] Feedback Deep Deterministic Policy Gradient With Fuzzy Reward for Robotic Multiple Peg-in-Hole Assembly Tasks, [paper], [bibtex], sources: [hzm2016/Peg_in_hole_assembly].
• [2019 ICRA] Sim-to-Real Transfer Learning using Robustified Controllers in Robotic Tasks involving Complex Dynamics, [paper], [bibtex].
• [2019 ICLR] The Neuro-Symbolic Concept Learner: Interpreting Scenes Words and Sentences from Natural Supervision, [paper], [bibtex], [homepage], sources: [vacancy/NSCL-PyTorch-Release].